The Agent Skills Directory

[SAFE]: The skill contains only documentation within SKILL.md and does not bundle any executable code, scripts, or binary assets.
[SAFE]: The skill configuration employs the allowed-tools frontmatter field to enforce a restricted scope, limiting execution permissions exclusively to the runcomfy command.
[SAFE]: Authentication details are discussed using standard, safe text placeholders rather than exposing actual credentials or sensitive tokens.
[SAFE]: The documentation includes proactive security guidance regarding prompt injection mitigations and input boundaries when handling third-party parameters.

ai-image-generation